In order to achieve autonomous lower limb rehabilitation training for stroke patients, exoskeletons are gradually combined with brain computer interface (BCI). Still, multi-class motor imagery (MI) electroencephalogram (EEG) has always had characteristics of difficulty in extraction and low recognition accuracy. A multi-classification optimized support vector machine algorithm for EEG signals based on wavelet independent component analysis(WICA) and common spatial patterns(CSP) is proposed. Particle swarm optimization (PSO) was used to train a support vector machine for classification. It proves that the algorithm can effectively extract EEG features and has a better recognition effect of motor imagery EEG signals. The feasibility of online and real-time EEG control was verified by combining motor imagery and exoskeleton devices。